Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    opinion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    HA
    -0.07
     Weg
    -0.06
     intoxic
    -0.06
    inus
    -0.06
     stabilize
    -0.06
    CHAIN
    -0.06
     xảy
    -0.06
     wrapping
    -0.06
    _ve
    -0.06
    른
    -0.06
    POSITIVE LOGITS
    +");↵
    0.07
    .Reference
    0.07
    ظه
    0.07
     IMPORTANT
    0.06
     serait
    0.06
    	click
    0.06
    เธอ
    0.06
    .click
    0.06
     ')↵
    0.06
     reluctant
    0.06
    Act Density 0.001%

    No Known Activations